EAGER: Individualized Musculoskeletal Modeling for Diagnosis, Rehabilitation and Real-time Feedback

该项目的目标是通过创建基于关节指数公式的产品的数据驱动模型，极大地改善肌肉骨骼建模的执行和利用方式。采用参数拟合的方法，可以对关节的运动链进行个体拟合，而不是采用不考虑人体形状和尺寸差异的通用模板。该团队将研究一种结构化的、数据驱动的方法来建模一个人，使其能够比较关节范围和肌肉限制，无论是对侧的，还是与同龄人的。还可以将患者与其过去的病史进行比较，以便更好地了解和诊断特定患者群体（脊柱侧凸、老年人、髋关节置换术康复）以及与一般人群的情况。该算法提出了一种基于不同动力模式分割的混合最优控制方法。这些模式可以考虑到质量或几何约束的变化，如辅助设备（如拐杖、助行器或外骨骼）。他们建议将这些肌肉骨骼建模方法应用于肌肉无力、关节损伤和可能需要人工假肢的老年人上肢。根据这一建议开发的工具可以通过以类似的方式建模它们的关节来用于分析任何数量的生物。它扩展到一个更广泛的机器人社区，机器人的运动链可以直接与生物链进行比较。这可以用于机器人设备的远程操作，其中特定的关节可以在彼此之间映射。它还增加了可用于设计辅助外骨骼和假体设备的工具，因为它允许生物和机械关节一起建模-潜在地改进控制这些设备的方法。项目团队由来自计算机科学的PI和两个顾问组成，一个来自机械工程（UC Berkeley），一个来自UCDMC的MD，他们在工作空间评估技术、人类建模、人机交互和控制方面拥有丰富的经验。研究结果还将通过大学的各种官方活动向K-12学生及其家长宣传。加州大学伯克利分校的社会利益信息技术研究中心（CITRIS）为研究人员提供了一个独特的环境和机会，让他们与其他研究人员、学生和更广泛的公众进行互动和分享研究成果。

The goal of this project is to vastly improve the way musculosketal modeling is performed and utilized by creating a data driven model that builds on the product of exponentials formulation for joints. By using parameter fitting, a kinematic chain of joints can be fitted the individual rather than scaling a generic template which does not take into account the large diversity in body shapes and sizes. The team will look at a structured, yet data driven approach to modeling a person, making it possible to compare joint ranges and muscular limitations both contralaterally, as well as against their peers. It is also possible to compare a patient and against their past history allowing for better understanding and diagnosis within a specified patient groups (scoliosis, the elderly, hip replacement recovery) as well as with the general population. The PI proposes a hybrid optimal control approach for determining muscular activation based on segmenting different dynamical modes. These modes can take into account changes in mass or geometric constraints such as assistive devices (e.g. crutches walkers or exoskeletons). They propose to apply these methods of musculoskeletal modeling to the upper limbs in the elderly group who experiences muscle weakness, joint damage and may have artificial prostheses.The tools developed under this proposal can be used to analyze any number of biological creatures by modeling their joints in a similar manner. It expands to a wider robotic community where robotic kinematic chains can be directly compared to biological chains. This can be used for teleoperation of robotic devices where particular joints can be mapped between each other. It also adds to the tools that can be used to design assistive exoskeletons and prosthetic devices, as it allows biological and mechanical joints to be modeled in together- potentially improving the methods of controlling these devices. The project team consists of a PI from Computer Science and two consultants, one from Mechanical Engineering (UC Berkeley) and a MD from UCDMC who have extensive experience in workspace assessment techniques, human modeling, human-machine interaction, and control. Research findings will also be outreached to K-12 students and their parents though various official events at the University. The Center for Information Technology Research in the Interest of Society (CITRIS) at UC Berkeley provides a unique environment and opportunity for the investigators to interact and share research findings with other researchers, students, and broader public.